Ms. Jieying Xue (3rd-year doctoral student in Nguyen Lab, Computing Science Research Area) and her team received the Best System Description Award at the 19th International Workshop on Semantic Evaluation (SemEval-2025).

SemEval is a series of international natural language processing (NLP) research workshops whose mission is to advance the current state of the art in semantic analysis and to help create high-quality annotated datasets in a range of increasingly challenging problems in natural language semantics.
SemEval-2025 was held from July 31 to August 1, 2025, in Vienna, Austria, as a part of ACL 2025 (the Annual Meeting of the Association for Computational Linguistics), one of the leading international conferences in the NLP field.
The award was presented to the team whose system description paper was recognized as the most outstanding among all participants in SemEval-2025 Task 11,"Bridging the Gap in Text-Based Emotion Detection."

＊Reference：SemEval-2025

■Date Awarded
August 1, 2025

■Title
Cross-Lingual Multi-Label Emotion Detection Using Generative Models

■Team Name and Members
JNLP：Jieying Xue, Phuong Minh Nguyen, Minh Le Nguyen, Xin Liu

■Abstract
With the rapid advancement of global digitalization, users from different countries increasingly rely on social media for information exchange. In this context, multilingual multi-label emotion detection has emerged as a critical research area. This study addresses SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection. Our paper focuses on two sub-tracks of this task: (1) Track A: Multi-label emotion detection, and (2) Track B: Emotion intensity. To tackle multilingual challenges, we leverage pre-trained multilingual models and focus on two architectures: (1) a fine-tuned BERT-based classification model and (2) an instruction-tuned generative LLM. Additionally, we propose two methods for handling multi-label classification: the base method, which maps an input directly to all its corresponding emotion labels, and the pairwise method, which models the relationship between the input text and each emotion category individually. Experimental results demonstrate the strong generalization ability of our approach in multilingual emotion recognition. In Track A, our method achieved Top 4 performance across 10 languages, ranking 1st in Hindi. In Track B, our approach also secured Top 5 performance in 7 languages, highlighting its simplicity and effectiveness.

■Comment
We are deeply honored to receive this award. We sincerely thank our professor for his invaluable guidance, our collaborators for their dedication and teamwork, and JAIST for providing essential computational resources. This recognition reflects not only our research efforts but also the strong support and collaboration that made this achievement possible.

September 29, 2025